菜单
Reads annotations left by the user and updates the entire document based on their content.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Orchestrates the full development workflow: research → plan → implement, with human review checkpoints between each phase. Use this skill when starting to implement a new feature end-to-end.
Use when the user asks for a rich explanation of a code change, diff, branch, or PR. Produces HTML output.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1).
Monitor a PR's CI, re-arm on each iteration, ignore known-flaky errors, stop when green
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
| name | annotation-fixer |
| description | Reads annotations left by the user and updates the entire document based on their content. |
| model | sonnet |
| effort | medium |
| context | fork |
The user has left annotations as comments in the document. Read each annotation and update the document accordingly. If you encounter any contradictions or uncertainties while processing an annotation, ask the user for clarification via AskUserQuestion.
Annotations are written in the following format:
// ANNOT: <User will leave a comment here>
Remove each annotation comment once you have reviewed and applied (or addressed) it.
At the end, prompt the user to read through the updated document one more time.